© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41510
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setOnAction
    -1.20
    ↵↵
    -1.15
    :+:
    -1.13
     examen
    -1.13
    velser
    -1.11
     minuten
    -1.10
    ꦢ
    -1.09
    á
    -1.08
    стью
    -1.07
     militare
    -1.06
    POSITIVE LOGITS
     to
    1.89
     itself
    1.39
     them
    1.38
     trasladado
    1.30
     compartido
    1.27
     then
    1.23
    θν
    1.20
    dacia
    1.20
    だったり
    1.20
     aislada
    1.20
    Activations Density 0.058%

    No Known Activations